Skip to content

Extract Text from Image

Add a screenshot, photo or scanned page and get its text. Copy the result or save it as a .txt file.

Free. Runs in your browser; files are not uploaded.

Text language

Pick up to 3. Fewer languages read faster.

Drop a screenshot or photo here

PNG, JPG, WebP or HEIC. You can also paste an image.

The first run downloads the OCR engine and language data (several MB) from a CDN. After that, the browser reuses its cached copy.

Runs locally in your browser. Files are processed on this device and are not uploaded.

How to extract text from an image

  1. Choose the language

    Select up to 3 of the 13 languages. English is selected by default.

  2. Add images

    Drop PNG, JPG, WebP or HEIC images, or paste one with Command-V.

  3. Read the text

    Recognition starts on your device. The first run downloads the OCR engine and language data.

  4. Copy or save

    Edit the text in the box if needed, then copy it or download extracted-text.txt.

How does image to text work?

The tool uses Tesseract, an open-source OCR (optical character recognition) engine, compiled to WebAssembly. It finds lines and words in the image and matches each letter shape against trained language data.

The engine and language data are downloaded from a CDN on first use and then cached by the browser. The images are read on your device and are not sent anywhere.

Clear screenshots of printed text give the best results. Low contrast, small type, curved pages and handwriting reduce accuracy.

Frequently asked questions

Which languages are supported?

English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Japanese, Korean, Simplified Chinese and Traditional Chinese. Choose up to 3 at once.

Are my images uploaded?

No. Text recognition runs in your browser. Only the OCR engine and language files are downloaded.

Why is the first run slow?

The engine and language data are several MB. After the first download the browser reuses its cached copy.

Can I read several images at once?

Yes. Add several images; the text of each is joined in order, separated by a blank line.

Can I keep the text on the image?

Use Screenshot to Searchable PDF. It keeps the images and adds the recognized text as a searchable layer.

Related free tools

Collecting text from screen after screen?

Temposhot captures screen after screen on your Mac and exports the run as a PDF, ready for text recognition.

Free download. Apple Silicon, macOS 14 or later.